Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    actions and statuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciencias
    0.51
    E
    0.51
    과학
    0.51
    Liter
    0.49
    science
    0.48
     scienza
    0.47
     E
    0.47
     science
    0.47
     sciences
    0.47
    sciences
    0.47
    POSITIVE LOGITS
     Follow
    0.40
     FOLLOW
    0.39
     Friendly
    0.38
     Keyboard
    0.38
     অবহিত
    0.37
     Organize
    0.37
    ಘ
    0.37
     Configure
    0.37
     Treatment
    0.36
     griego
    0.36
    Act Density 0.000%

    No Known Activations